SOTAVerified

Point Cloud Super Resolution

Point cloud super-resolution is a fundamental problem for 3D reconstruction and 3D data understanding. It takes a low-resolution (LR) point cloud as input and generates a high-resolution (HR) point cloud with rich details

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 16 papers

TitleStatusHype
PUGeo-Net: A Geometry-centric Network for 3D Point Cloud UpsamplingCode1
Lightweight super resolution network for point cloud geometry compressionCode1
Meta-PU: An Arbitrary-Scale Upsampling Network for Point CloudCode1
Frequency-Selective Mesh-to-Mesh Resampling for Color Upsampling of Point Clouds—0
SRMamba: Mamba for Super-Resolution of LiDAR Point Clouds—0
Diffusion-Based Point Cloud Super-Resolution for mmWave Radar Data—0
EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera—0
PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation—0
R2LDM: An Efficient 4D Radar Super-Resolution Framework Leveraging Diffusion Model—0
PU-GAN: a Point Cloud Upsampling Adversarial NetworkCode0
Show:102550
← PrevPage 1 of 2Next →
All datasetsSHREC15PU-GAN

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Meta-PUF-measure (%)94.96—Unverified
2AR-GCNF-measure (%)93.1—Unverified
3PU-NETF-measure (%)56.4—Unverified
#ModelMetricClaimedVerifiedStatus
1PU-MFAChamfer Distance0.23—Unverified